{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:5YPKCWVCTC5UEZ5LJSTM4RSPZI","short_pith_number":"pith:5YPKCWVC","schema_version":"1.0","canonical_sha256":"ee1ea15aa298bb4267ab4ca6ce464fca29891ff4793ec8c392f42591693e84d6","source":{"kind":"arxiv","id":"1906.01617","version":1},"attestation_state":"computed","paper":{"title":"Self-Attentional Models for Lattice Inputs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alex Waibel, Graham Neubig, Matthias Sperber, Ngoc-Quan Pham","submitted_at":"2019-06-04T17:51:03Z","abstract_excerpt":"Lattices are an efficient and effective method to encode ambiguity of upstream systems in natural language processing tasks, for example to compactly capture multiple speech recognition hypotheses, or to represent multiple linguistic analyses. Previous work has extended recurrent neural networks to model lattice inputs and achieved improvements in various tasks, but these models suffer from very slow computation speeds. This paper extends the recently proposed paradigm of self-attention to handle lattice inputs. Self-attention is a sequence modeling technique that relates inputs to one another"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1906.01617","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-04T17:51:03Z","cross_cats_sorted":[],"title_canon_sha256":"ee7b7c9a8cb244cf8177573922252857fe4cdaed92504573530b76824295f336","abstract_canon_sha256":"dd81fda470bb8ba80af6be2671af51df5e39613b3a94d2cb7eb6f6b60dccfc96"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:15.948454Z","signature_b64":"md5ZQ6I7JP35TI90KBFFbiOIDu/QOuf0bP8ddLuPgV/FAF3UlsMfw21KmdKLI9IpY4wAyNkq/NnotTBPjwf2CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee1ea15aa298bb4267ab4ca6ce464fca29891ff4793ec8c392f42591693e84d6","last_reissued_at":"2026-05-17T23:44:15.947803Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:15.947803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Attentional Models for Lattice Inputs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alex Waibel, Graham Neubig, Matthias Sperber, Ngoc-Quan Pham","submitted_at":"2019-06-04T17:51:03Z","abstract_excerpt":"Lattices are an efficient and effective method to encode ambiguity of upstream systems in natural language processing tasks, for example to compactly capture multiple speech recognition hypotheses, or to represent multiple linguistic analyses. Previous work has extended recurrent neural networks to model lattice inputs and achieved improvements in various tasks, but these models suffer from very slow computation speeds. This paper extends the recently proposed paradigm of self-attention to handle lattice inputs. Self-attention is a sequence modeling technique that relates inputs to one another"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.01617","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1906.01617","created_at":"2026-05-17T23:44:15.947902+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.01617v1","created_at":"2026-05-17T23:44:15.947902+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.01617","created_at":"2026-05-17T23:44:15.947902+00:00"},{"alias_kind":"pith_short_12","alias_value":"5YPKCWVCTC5U","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"5YPKCWVCTC5UEZ5L","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"5YPKCWVC","created_at":"2026-05-18T12:33:10.108867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5YPKCWVCTC5UEZ5LJSTM4RSPZI","json":"https://pith.science/pith/5YPKCWVCTC5UEZ5LJSTM4RSPZI.json","graph_json":"https://pith.science/api/pith-number/5YPKCWVCTC5UEZ5LJSTM4RSPZI/graph.json","events_json":"https://pith.science/api/pith-number/5YPKCWVCTC5UEZ5LJSTM4RSPZI/events.json","paper":"https://pith.science/paper/5YPKCWVC"},"agent_actions":{"view_html":"https://pith.science/pith/5YPKCWVCTC5UEZ5LJSTM4RSPZI","download_json":"https://pith.science/pith/5YPKCWVCTC5UEZ5LJSTM4RSPZI.json","view_paper":"https://pith.science/paper/5YPKCWVC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.01617&json=true","fetch_graph":"https://pith.science/api/pith-number/5YPKCWVCTC5UEZ5LJSTM4RSPZI/graph.json","fetch_events":"https://pith.science/api/pith-number/5YPKCWVCTC5UEZ5LJSTM4RSPZI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5YPKCWVCTC5UEZ5LJSTM4RSPZI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5YPKCWVCTC5UEZ5LJSTM4RSPZI/action/storage_attestation","attest_author":"https://pith.science/pith/5YPKCWVCTC5UEZ5LJSTM4RSPZI/action/author_attestation","sign_citation":"https://pith.science/pith/5YPKCWVCTC5UEZ5LJSTM4RSPZI/action/citation_signature","submit_replication":"https://pith.science/pith/5YPKCWVCTC5UEZ5LJSTM4RSPZI/action/replication_record"}},"created_at":"2026-05-17T23:44:15.947902+00:00","updated_at":"2026-05-17T23:44:15.947902+00:00"}